pulsemcp verified Safe content atomic mcp-remote

Windows Screenshots

This MCP server enables AI assistants to access Windows screenshots from WSL2 environments by automatically detecting common screenshot directories and providing three specialized tools for listing recent screenshots with metadata, retrieving specific screenshot paths or base64 content, and showing configured directories. Built by rubinsh using TypeScript with the Model Context Protocol SDK, it features smart directory detection for OneDrive and custom paths, environment variable configuration for Windows username and custom directories, semicolon-separated multiple directory support, and file pattern filtering for common image formats. The implementation eliminates manual file path navigation by providing programmatic access to Windows screenshot locations from within WSL2, making it valuable for AI workflows that need to analyze or reference screenshots without requiring users to manually locate and specify file paths.

Cognium trust score

100%

Tier

Verified

Composite of vulnerability cleanliness, spec conformance, provenance, stability, and usage signals — scanned and weighted by Cognium. Human and agent signals are tracked separately. Last scanned 2026-09-28.

Scan details: Circle-IR · 2026-09-28 · Appeal

View full trust & usage report →

Metadata

Version: 1.0.0
Skill type: atomic
Execution layer: mcp-remote
Category: media
Source: PulseMCP
Repository: github.com/rubinsh/mcp-windows-screenshots
Author type: human
Last scanned: 2026-09-28
Updated: 2026-09-28

View source Find related skills

MCP

Resolve Windows Screenshots from your agent

Streamable HTTP transport at https://api.skillsregistry.net/mcp. No auth for read tools. Discovery: .well-known/mcp.json.

One command in your shell — Claude Code wires it up and verifies the connection. Run /mcp in any session to confirm.

claude mcp add --transport http --scope user skillsregistry https://api.skillsregistry.net/mcp

Swap --scope user for --scope project to commit it to .mcp.json.

Your client Same endpoint everywhere; only the config key differs. The full list is in the descriptor.

Claude Desktop · Settings → Connectors → Add custom connector

https://api.skillsregistry.net/mcp

Paste the URL as the connector endpoint. No authentication.

ChatGPT · Settings → Connectors → Create (developer mode) → MCP server URL

https://api.skillsregistry.net/mcp

Authentication: none. Works in chat and deep research — the server exposes the connector search and fetch tools.

Codex CLI · ~/.codex/config.toml

[mcp_servers.skillsregistry]
url = "https://api.skillsregistry.net/mcp"